# Awesome MLSecOps

> MLSecOps (Machine Learning Security Operations) integrates security engineering, threat modeling, testing, supply-chain controls, monitoring, and incident response across the machine-learning lifecycle. It protects data, models, pipelines, infrastructure, LLM applications, and AI agents against poisoning, adversarial manipulation, unsafe artifacts, privacy leakage, model extraction, prompt injection, and excessive agency.

Last updated: 2026-07-29
Canonical site: https://awesomemlsecops.com/
Canonical community catalog: https://github.com/RiccardoBiosas/awesome-MLSecOps

Use the human-readable pages below as citation sources. The GitHub repository is the source of truth for catalog inclusion.

## Core Pages

- [Awesome MLSecOps](https://awesomemlsecops.com/): Hub for MLSecOps definitions, categories, jobs, and newsletter discovery.
- [What is MLSecOps?](https://awesomemlsecops.com/what-is-mlsecops/): Canonical definition, lifecycle, operating model, and concise FAQ answers.
- [MLSecOps FAQ](https://awesomemlsecops.com/faq/): Direct answers about machine learning, LLM, agent, supply-chain, and privacy security.
- [MLSecOps vs DevSecOps](https://awesomemlsecops.com/mlsecops-vs-devsecops/): Comparison of scopes, assets, controls, evidence, and ownership.
- [MLSecOps tools](https://awesomemlsecops.com/tools/): Index of category guides generated from the GitHub catalog.
- [AI and ML security jobs](https://awesomemlsecops.com/jobs/): 12 current, expiry-filtered roles.
- [The MLSecOps Hacker newsletter](https://awesomemlsecops.com/newsletter/): Subscription form and dated issue archive.

## Tool Category Pages

- [LLM Security and Red Teaming](https://awesomemlsecops.com/tools/llm-security/): Test prompts, model behavior, guardrails, and application controls against abuse. 19 catalog entries.
- [Model Scanning and Validation](https://awesomemlsecops.com/tools/model-scanning/): Inspect model files, notebooks, code, and behavior before release or deployment. 13 catalog entries.
- [Adversarial Machine Learning](https://awesomemlsecops.com/tools/adversarial-ml/): Evaluate evasion, poisoning, extraction, inversion, and model robustness. 19 catalog entries.
- [AI Supply-Chain Security](https://awesomemlsecops.com/tools/supply-chain/): Protect model provenance, artifacts, dependencies, signing, and delivery pipelines. 6 catalog entries.
- [AI Agent and MCP Security](https://awesomemlsecops.com/tools/agent-security/): Secure agent tools, memory, identity, permissions, sandboxes, and MCP servers. 5 catalog entries.
- [Privacy-Preserving Machine Learning](https://awesomemlsecops.com/tools/privacy/): Reduce sensitive-data exposure and test privacy leakage in ML systems. 12 catalog entries.

## Newsletter Issues

- [AI Security: Model Serialization Attacks](https://themlsecopshacker.com/p/ai-security-model-serialization-attacks): A practical review of model serialization risks, machine learning supply-chain vulnerabilities, and defensive practices for handling model artifacts safely.
- [What is MLSecOps?](https://themlsecopshacker.com/p/what-is-mlsecops): An introduction to the discipline of securing machine learning systems and the teams, controls, and operating practices that support it.

## Machine-Readable Discovery

- [Tools JSON](https://awesomemlsecops.com/tools.json): Full typed catalog with stable IDs, source-bounded directory descriptions, category guides, and first-party source URLs.
- [Newsletter RSS](https://awesomemlsecops.com/rss.xml): Feed of dated newsletter archive entries.
- [XML sitemap](https://awesomemlsecops.com/sitemap.xml): Index of canonical human-readable routes.
- [Crawler policy](https://awesomemlsecops.com/robots.txt): Search and AI crawler access policy.